Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1356 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1865. Min Act: -0.0001

Data Index: 1447139 (Python Code)

Max Activating Token Index: 869

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1556263 (Python Code)

Max Activating Token Index: 219

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1743. Min Act: -0.0001

Data Index: 1490974 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1611. Min Act: -0.0001

Data Index: 1557902 (Python Code)

Max Activating Token Index: 146

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1562. Min Act: -0.0001

Data Index: 1486262 (Python Code)

Max Activating Token Index: 773

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1765. Min Act: -0.0001

Data Index: 1423969 (Python Code)

Max Activating Token Index: 133

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1470081 (Python Code)

Max Activating Token Index: 200

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1646679 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1646. Min Act: -0.0001

Data Index: 1602725 (Python Code)

Max Activating Token Index: 967

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1596. Min Act: -0.0001

Data Index: 1423283 (Python Code)

Max Activating Token Index: 483

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1499147 (Python Code)

Max Activating Token Index: 665

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1728. Min Act: -0.0001

Data Index: 1384087 (Python Code)

Max Activating Token Index: 617

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1451902 (Python Code)

Max Activating Token Index: 323

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1734. Min Act: -0.0001

Data Index: 1543197 (Python Code)

Max Activating Token Index: 358

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1392752 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1768. Min Act: -0.0001

Data Index: 1439839 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1563. Min Act: -0.0001

Data Index: 1371801 (Python Code)

Max Activating Token Index: 904

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1470620 (Python Code)

Max Activating Token Index: 299

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1461111 (Python Code)

Max Activating Token Index: 66

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1375226 (Python Code)

Max Activating Token Index: 782